ClawHub
Back to skill

Security audit

openclaw ollama memory

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only guide for configuring local OpenClaw memory search with Ollama, with one privacy note around optional extra indexing paths.

Install only if you want OpenClaw memory search to use local Ollama embeddings. Review any extraPaths carefully, since those directories can be recursively indexed into memory search; avoid secrets, private notes, unrelated team folders, or broad absolute paths unless that is intentional.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The documentation explicitly encourages indexing directories outside the default workspace via extraPaths, including absolute paths, but provides no warning that this broadens the memory corpus to potentially sensitive files. In a semantic memory system, accidental inclusion of shared notes, team docs, or other non-workspace markdown can expose private or unrelated content to later queries, causing confidentiality and scope-boundary violations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.